Please provide complete information as applicable to your setup.
• Hardware Platform ( GPU)
• DeepStream Version 4.0
• TensorRT Version : 6.0
• NVIDIA GPU Driver Version 10.1
I wrote a plug-in based on dsexample and nvsegvisual source code, the purpose is to enlarge the input video frame 4 times, and then output, I tested the plug-in in gst-lanch works properly, but after integrated into deepstream-app, no matter what video is processed, After processing 1024 frames, it stopped magically. By looking at the source code of deepstream-app, I didn’t find a solution, so I came to ask for help，many thanks.